| From: | Martijn van Oosterhout <kleptog(at)svana(dot)org> |
|---|---|
| To: | Bruce Momjian <pgman(at)candle(dot)pha(dot)pa(dot)us> |
| Cc: | Marshall Spight <marshall(at)meetstheeye(dot)com>, pgsql-general(at)postgresql(dot)org |
| Subject: | Re: How to make a REALLY FAST db server? |
| Date: | 2001-09-27 23:23:14 |
| Message-ID: | 20010928092314.B32426@svana.org |
| Views: | Raw Message | Whole Thread | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-general |
On Thu, Sep 27, 2001 at 03:35:09PM -0400, Bruce Momjian wrote:
> > Usually when this question is asked, the response is "well,
> > I've run a lot of servers, and they just seem faster." But I'm
> > only interested in hard data.
>
> Well, SCSI with tagged queueing allows you to send multiple disk
> requests to the drive and the drive orders them to be optimal. Only the
> drive knows there the head it at a given moment so it seems good to push
> such optimizations into the disk drive.
From what I gather from reading lkml, recent ATA standards do include such
capabilities. Whether it is supports by the drivers, controllers and disks
is another matter entirely. But it is there.
--
Martijn van Oosterhout <kleptog(at)svana(dot)org>
http://svana.org/kleptog/
> Magnetism, electricity and motion are like a three-for-two special offer:
> if you have two of them, the third one comes free.
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Martijn van Oosterhout | 2001-09-27 23:33:03 | Re: PostGres is not using indices in select, I would like it to because it is too slow ! |
| Previous Message | Martijn van Oosterhout | 2001-09-27 23:20:27 | Re: Performance question (stripped down the problem) |